Senior MCP / Agentic AI Specialist

Zuven Technologies Inc

Dallas, TX • 31m ago • On-site

Senior

On-site

  1. Select offer
  2. Add resume
  3. Analyze
  4. Improve
  5. Apply
  6. Auto-send · soon

Match your resume with similar open roles

Upload your resume to automatically match with active openings similar to this role.

PDF up to 10 MB

Your resume is private & secure

Or go to the original job offer

Quick Facts

  • Role: Senior MCP / Agentic AI Specialist (Agentic AI & Platform Engineering)
  • Focus: Design, build, and secure MCP infrastructure for autonomous LLM agents
  • Level: Senior / Staff

Description

You will own the Model Context Protocol (MCP) servers, clients, and tool-integration layers that let AI agents reliably retrieve context and take action safely at production scale. MCP enables structured access to external tools, data, and systems across major agent hosts. You will balance capability with containment while defending against threats such as tool poisoning, rug pulls, prompt injection via tool outputs, confused-deputy token abuse, and malicious or misbehaving agents.

Responsibilities

  • Build production MCP servers and clients implementing the specification (JSON-RPC 2.0, capability negotiation, Tools/Resources/Prompts, Sampling/Roots/Elicitation)
  • Implement and operate MCP transports (stdio, Streamable HTTP; migrate away from legacy HTTP+SSE while preserving backward compatibility)
  • Integrate MCP servers into real hosts/connectors (Claude, ChatGPT, Cursor, and others), handling connection models and authentication flows
  • Create external system connectors for databases, SaaS APIs, and internal services with authentication, pagination, rate limits, retries, and error recovery
  • Secure the MCP tool layer against ecosystem-specific attacks (tool poisoning, rug pulls, tool shadowing/cross-origin escalation, prompt injection, data exfiltration)
  • Implement OAuth 2.1 for remote MCP servers (PKCE, resource indicators, audience validation), validate tokens per request, and prevent token leakage to upstream APIs
  • Add rogue-agent containment (sandboxing/isolation, least-privilege deny-by-default permissions, egress allowlisting, human-in-the-loop approvals, kill-switches)
  • Build and optimize agent orchestration and interoperability using agent frameworks (single-agent and multi-agent workflows)
  • Publish and manage MCP servers through the official MCP registry/private sub-registries with version pinning and an approved-server catalog
  • Ensure production reliability and observability (health checks, timeouts, retries, circuit breakers, tracing/metrics, graceful degradation) and optimize cost
  • Build evaluation harnesses, test datasets, and benchmarks for accuracy, tool-call reliability, latency, and safety regression detection
  • Provide technical leadership, mentor engineers, and shape best practices for agent/tool security

Requirements

  • 6+ years of software engineering, backend/distributed systems, or ML/platform engineering
  • Hands-on experience with MCP (servers/clients, tool schema design, transports and MCP primitives)
  • Experience integrating MCP into production hosts/connectors and exposing external systems as tools
  • Strong grasp of MCP/LLM agent security and mitigations (tool poisoning, rug pulls, prompt injection, confused-deputy/OAuth, supply-chain risk)
  • Hands-on with OAuth 2.1/OIDC (PKCE, resource indicators, audience validation), secrets management, and least-privilege design
  • Experience building LLM-powered applications (tool/function calling, prompt design, RAG, context/token management)
  • Familiarity with at least one agent framework (LangGraph, AutoGen, CrewAI, LlamaIndex, OpenAI Agents SDK, Anthropic agent SDK)
  • Strong REST/JSON-RPC 2.0/WebSockets/SSE integration skills and robust error handling
  • Expert in Python and/or TypeScript; Go or Rust preferred
  • Experience deploying and operating services on AWS/GCP/Azure with containers/Kubernetes and observability

Benefits

  • Senior/Staff technical ownership and leadership in a fast-moving agentic AI domain

See similar jobs

Explore similar jobs and use your resume score to choose where to apply next

See more

Unlock Full Resume Report